Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    javascript and python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    谿
    0.38
    鶉
    0.35
    плення
    0.34
    ≾
    0.33
    ्यर्थ
    0.33
    巖
    0.33
    簟
    0.33
    ष्मा
    0.32
    Ꮈ
    0.32
     পারস্প
    0.32
    POSITIVE LOGITS
    try
    0.45
    '
    0.44
    //
    0.44
    ↵↵
    0.42
    0.42
    ----------------
    0.41
        
    0.41
     try
    0.41
     //
    0.40
    -
    0.40
    Act Density 0.018%

    No Known Activations